Explore the vast range of titles available.

Our paper compares the correctness, efficiency, and maintainability of human-generated and AI-generated program code. For that, we analyzed the computational resources of AI- and human-generated program code using metrics such as time and space complexity as well as runtime and memory usage. Additionally, we evaluated the maintainability using metrics such as lines of code, cyclomatic complexity, Halstead complexity and maintainability index. For our experiments, we had generative AIs produce program code in Java, Python, and C++ that solves problems defined on the competition coding website leetcode.com. We selected six LeetCode problems of varying difficulty, resulting in 18 program codes generated by each generative AI. GitHub Copilot, powered by Codex (GPT-3.0), performed best, solving 9 of the 18 problems (50.0%), whereas CodeWhisperer did not solve a single problem. BingAI Chat (GPT-4.0) generated correct program code for seven problems (38.9%), ChatGPT (GPT-3.5) and Code Llama (Llama 2) for four problems (22.2%) and StarCoder and InstructCodeT5+ for only one problem (5.6%). Surprisingly, although ChatGPT generated only four correct program codes, it was the only generative AI capable of providing a correct solution to a coding problem of difficulty level hard. In summary, 26 AI-generated codes (20.6%) solve the respective problem. For 11 AI-generated incorrect codes (8.7%), only minimal modifications to the program code are necessary to solve the problem, which results in time savings between 8.9% and even 71.3% in comparison to programming the program code from scratch.

Running machine learning algorithms for image classification locally on small, cheap, and low-power microcontroller units (MCUs) has advantages in terms of bandwidth, inference time, energy, reliability, and privacy for different applications. Therefore, TinyML focuses on deploying neural networks on MCUs with random access memory sizes between 2 KB and 512 KB and read-only memory storage capacities between 32 KB and 2 MB. Models designed for high-end devices are usually ported to MCUs using model scaling factors provided by the model architecture’s designers. However, our analysis shows that this naive approach of substantially scaling down convolutional neural networks (CNNs) for image classification using such default scaling factors results in suboptimal performance. Consequently, in this paper we present a systematic strategy for efficiently scaling down CNN model architectures to run on MCUs. Moreover, we present our CNN Analyzer, a dashboard-based tool for determining optimal CNN model architecture scaling factors for the downscaling strategy by gaining layer-wise insights into the model architecture scaling factors that drive model size, peak memory, and inference time. Using our strategy, we were able to introduce additional new model architecture scaling factors for MobileNet v1, MobileNet v2, MobileNet v3, and ShuffleNet v2 and to optimize these model architectures. Our best model variation outperforms the MobileNet v1 version provided in the MLPerf Tiny Benchmark on the Visual Wake Words image classification task, reducing the model size by 20.5% while increasing the accuracy by 4.0%.

The automated transcription of mathematical formulas represents a complex challenge that is of great importance for digital processing and comprehensibility of mathematical content. Consequently, our goal was to analyze state-of-the-art approaches for the transcription of printed mathematical formulas on images into spoken English text. We focused on two approaches: (1) The combination of mathematical expression recognition (MER) models and natural language processing (NLP) models to convert formula images first into LaTeX code and then into text, and (2) the direct conversion of formula images into text using vision-language (VL) models. Since no dataset with printed mathematical formulas and corresponding English transcriptions existed, we created a new dataset, Formula2Text, for fine-tuning and evaluating our systems. Our best system for (1) combines the MER model LaTeX-OCR and the NLP model BART-Base, achieving a translation error rate of 36.14% compared with our reference transcriptions. In the task of converting LaTeX code to text, BART-Base, T5-Base, and FLAN-T5-Base even outperformed ChatGPT, GPT-3.5 Turbo, and GPT-4. For (2), the best VL model, TrOCR, achieves a translation error rate of 42.09%. This demonstrates that VL models, predominantly employed for classical image captioning tasks, possess significant potential for the transcription of mathematical formulas in images.

French is a strategically and economically important language in the regions where the African language Twi is spoken. However, only a very small proportion of Twi speakers in Ghana speak French. The development of a Twi–French parallel corpus and corresponding machine translation applications would provide various advantages, including stimulating trade and job creation, supporting the Ghanaian diaspora in French-speaking nations, assisting French-speaking tourists and immigrants seeking medical care in Ghana, and facilitating numerous downstream natural language processing tasks. Since there are hardly any machine translation systems or parallel corpora between Twi and French that cover a modern and versatile vocabulary, our goal was to extend a modern Twi–English corpus with French and develop machine translation systems between Twi and French: Consequently, in this paper, we present our Twi–French corpus of 10,708 parallel sentences. Furthermore, we describe our machine translation experiments with this corpus. We investigated direct machine translation and cascading systems that use English as a pivot language. Our best Twi–French system is a direct state-of-the-art transformer-based machine translation system that achieves a BLEU score of 0.76. Our best French–Twi system, which is a cascading system that uses English as a pivot language, results in a BLEU score of 0.81. Both systems are fine tuned with our corpus, and our French–Twi system even slightly outperforms Google Translate on our test set by 7% relative.

Skills are the common ground between employers, job seekers and educational institutions which can be analyzed with the help of artificial intelligence (AI), specifically natural language processing (NLP) techniques. In this paper we explore a state-of-the-art pipeline that extracts, vectorizes, clusters, and compares skills to provide recommendations for all three players—thereby bridging the gap between employers, job seekers and educational institutions. As companies hiring data scientists report that it is increasingly difficult to find a so-called \"unicorn data scientist\" [1], we conduct our experiments and analysis using companies’ job postings for a data scientist position, job seekers’ CVs for that position, and a curriculum from a master's program in data science. However, our investigated methods and our final recommendation system can be applied to other job positions as well. Our best system combines Sentence-BERT [2], UMAP [3], DBSCAN [4], and K-means clustering [5]. To also evaluate feedback from potential users, we conducted a survey, in which the majority of employers’, job seekers’ and educational institutions’ representatives state that with the help of our automatic recommendations, processes related to skills are more effective, faster, fairer, more explainable, more autonomous and more supported.

Chatbots based on large language models (LLMs) like ChatGPT are available to the wide public. These tools can for instance be used by students to generate essays or whole theses from scratch or by rephrasing an existing text. But how does for instance a teacher know whether a text is written by a student or an AI? In this paper, we investigate perplexity , semantic , list lookup , document , error-based , readability , AI feedback and text vector features to classify human-generated and AI-generated texts from the educational domain as well as news articles. We analyze two scenarios: (1) The detection of text generated by AI from scratch, and (2) the detection of text rephrased by AI. Since we assumed that classification is more difficult when the AI has been prompted to create or rephrase the text in a way that a human would not recognize that it was generated or rephrased by an AI, we also investigate this advanced prompting scenario. To train, fine-tune and test the classifiers, we created the Multilingual Human-AI-Generated Text Corpus which contains human-generated , AI-generated and AI-rephrased texts from the educational domain in English, French, German, and Spanish and English texts from the news domain. We demonstrate that the same features can be used for the detection of AI-generated and AI-rephrased texts from the educational domain in all languages and the detection of AI-generated and AI-rephrased news texts. Our best systems significantly outperform GPTZero and ZeroGPT—state-of-the-art systems for the detection of AI-generated text. Our best text rephrasing detection system even outperforms GPTZero by 181.3% relative in F1-score.

Spacecraft operations are highly critical, demanding impeccable reliability and safety. Ensuring the optimal performance of a spacecraft requires the early detection and mitigation of anomalies, which could otherwise result in unit or mission failures. With the advent of deep learning, a surge of interest has been seen in leveraging these sophisticated algorithms for anomaly detection in space operations. This study aims to compare the efficacy of various deep learning architectures in detecting anomalies in spacecraft data. The deep learning models under investigation include Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, and Transformer-based architectures. Each of these models was trained and validated using a comprehensive dataset sourced from multiple spacecraft missions, encompassing diverse operational scenarios and anomaly types. Initial results indicate that while CNNs excel in identifying spatial patterns and may be effective for some classes of spacecraft data, LSTMs and RNNs show a marked proficiency in capturing temporal anomalies seen in time-series spacecraft telemetry. The Transformer-based architectures, given their ability to focus on both local and global contexts, have showcased promising results, especially in scenarios where anomalies are subtle and span over longer durations. Additionally, considerations such as computational efficiency, ease of deployment, and real-time processing capabilities were evaluated. While CNNs and LSTMs demonstrated a balance between accuracy and computational demands, Transformer architectures, though highly accurate, require significant computational resources. In conclusion, the choice of deep learning architecture for spacecraft anomaly detection is highly contingent on the nature of the data, the type of anomalies, and operational constraints.

In recent years, AI systems in the medical domain have advanced significantly. However, despite outperforming humans, they are rarely used in practice since it is often not clear how they make their decisions. Optimal explanation and visualization of the decision process are often lacking. Therefore, we conducted a comparative user-centric analysis of the latest state-of-the-art textual, visual and multimodal explainable artificial intelligence (XAI) methods for medical image diagnosis. Our survey of 33 physicians showed that 88% agree that it is important that AI explains the diagnosis -- 64% even strongly agree. A combination of bounding box and report is rated better than the other tested XAI methods in the evaluated aspects understandability, completeness, speed, and applicability. We even tested the potential negative impact of false AI-based medical image diagnoses and found that 50% of the participants trusted false AI diagnoses over all tested XAI methods.

The evaluation of academic theses is a cornerstone of higher education, ensuring rigor and integrity. Traditional methods, though effective, are time-consuming and subject to evaluator variability. This paper presents RubiSCoT, an AI-supported framework designed to enhance thesis evaluation from proposal to final submission. Using advanced natural language processing techniques, including large language models, retrieval-augmented generation, and structured chain-of-thought prompting, RubiSCoT offers a consistent, scalable solution. The framework includes preliminary assessments, multidimensional assessments, content extraction, rubric-based scoring, and detailed reporting. We present the design and implementation of RubiSCoT, discussing its potential to optimize academic assessment processes through consistent, scalable, and transparent evaluation.

Empathy is often understood as the ability to share and understand another individual's state of mind or emotion. With the increasing use of chatbots in various domains, e.g., children seeking help with homework, individuals looking for medical advice, and people using the chatbot as a daily source of everyday companionship, the importance of empathy in human-computer interaction has become more apparent. Therefore, our study investigates the extent to which ChatGPT based on GPT-3.5 can exhibit empathetic responses and emotional expressions. We analyzed the following three aspects: (1) understanding and expressing emotions, (2) parallel emotional response, and (3) empathic personality. Thus, we not only evaluate ChatGPT on various empathy aspects and compare it with human behavior but also show a possible way to analyze the empathy of chatbots in general. Our results show, that in 91.7% of the cases, ChatGPT was able to correctly identify emotions and produces appropriate answers. In conversations, ChatGPT reacted with a parallel emotion in 70.7% of cases. The empathic capabilities of ChatGPT were evaluated using a set of five questionnaires covering different aspects of empathy. Even though the results show, that the scores of ChatGPT are still worse than the average of healthy humans, it scores better than people who have been diagnosed with Asperger syndrome / high-functioning autism.